© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    conversational interaction between two people

    oai_token-act-pair · gemini-2.0-flash

    asking about you

    np_max-act · gemini-2.0-flash
    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
     فريبيس
    -0.65
    interopRequire
    -0.63
     бъдат
    -0.59
    OrBuilder
    -0.59
     financeiro
    -0.57
     שוליים
    -0.56
    下载附件
    -0.52
     [''],
    -0.52
    +:+
    -0.52
     jopa
    -0.52
    POSITIVE LOGITS
     continúas
    0.69
    ?
    0.63
    ؟
    0.58
    netbeans
    0.50
     sosp
    0.48
    hoy
    0.47
     PLWABN
    0.46
     gon
    0.46
    scape
    0.46
    RetentionPolicy
    0.46
    Activations Density 2.050%

    No Known Activations