© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4360
    Prev
    Next
    INDEX
    Explanations

    references to personal interactions between people

    oai_token-act-pair · gemini-2.0-flash

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.81
     ligiloj
    -0.62
    ButtonModule
    -0.56
    thenReturn
    -0.54
    RUnlock
    -0.53
    Vidite
    -0.52
    PasswordEncoder
    -0.50
    省市镇
    -0.50
    griffen
    -0.50
     ✭✭
    -0.49
    POSITIVE LOGITS
    RectangleBorder
    0.75
    WillAppear
    0.64
    InputBorder
    0.62
    TargetException
    0.59
    VersionUID
    0.59
    migrationBuilder
    0.58
     onCancelled
    0.57
    ,:),
    0.56
     ©️
    0.54
    })]
    0.52
    Activations Density 1.585%

    No Known Activations