© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2060
    Prev
    Next
    INDEX
    Explanations

    clauses including "had", "have", "more", and words indicating relationships.

    oai_token-act-pair · gemini-2.0-flash

    had/have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PerformLayout
    -0.67
     дописавши
    -0.59
    proven
    -0.55
    tanleria
    -0.55
    saraba
    -0.53
    Források
    -0.53
    Билгалдахарш
    -0.52
    ]--;
    -0.51
     незавершена
    -0.50
    rungsseite
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.52
    årige
    0.48
    NSData
    0.47
    InputTagHelper
    0.47
     caisse
    0.47
     educativas
    0.46
     répartition
    0.46
    FontStyle
    0.45
     işi
    0.45
    \{\\
    0.44
    Activations Density 7.055%

    No Known Activations