© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15503
    Prev
    Next
    INDEX
    Explanations

    section headers and programming code snippets

    oai_token-act-pair · gemini-2.0-flash

    background/row

    np_max-act · gemini-2.0-flash

    section headings

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     esternos
    -0.91
    GraphicsUnit
    -0.84
    TemporalType
    -0.79
    ftagPool
    -0.79
    ]")]
    -0.73
     referenties
    -0.71
    AndEndTag
    -0.70
    kuuta
    -0.67
    DataMember
    -0.67
    MLLoader
    -0.67
    POSITIVE LOGITS
     incluso
    0.49
    Purpose
    0.49
     even
    0.47
     Purpose
    0.45
    目的
    0.43
    之前
    0.43
    提
    0.41
    推
    0.41
    Ma
    0.41
    完
    0.40
    Activations Density 2.741%

    No Known Activations