© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15415
    Prev
    Next
    INDEX
    Explanations

    mentions of opinions, facts or reasons

    oai_token-act-pair · gemini-2.0-flash

    fact

    np_max-act · gemini-2.0-flash

    fact Method used: 1 — because max-activating tokens are identical

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.66
    aarrggbb
    -0.65
    ValueStyle
    -0.60
    GenerationType
    -0.58
    ьаж
    -0.56
    DotNetBar
    -0.56
     apologize
    -0.55
    TabIndex
    -0.55
    SerializedSize
    -0.52
    évaluateur
    -0.51
    POSITIVE LOGITS
     MainAxisSize
    0.67
     bahawa
    0.65
     Leute
    0.65
     dedans
    0.61
     />';
    0.59
     realising
    0.59
    inburgh
    0.59
     RIPRODUZIONE
    0.59
     internetowa
    0.59
     îna
    0.59
    Activations Density 1.785%

    No Known Activations