© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7354
    Prev
    Next
    INDEX
    Explanations

    sentences indicating negative sentiment

    oai_token-act-pair · gemini-2.0-flash

    Negation in programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     not
    -0.66
     isn
    -0.63
    not
    -0.55
     cannot
    -0.55
     exceedingly
    -0.53
    glEnd
    -0.53
     niet
    -0.53
     aint
    -0.52
     incredibly
    -0.51
    fone
    -0.51
    POSITIVE LOGITS
    EndProject
    0.71
    DrawerToggle
    0.59
    djangoproject
    0.59
    клопе
    0.58
    RenderAtEndOf
    0.56
    AndEndTag
    0.56
    VersionUID
    0.56
    JsonPropertyName
    0.52
     assim
    0.52
    GenerationType
    0.52
    Activations Density 1.007%

    No Known Activations