© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12927
    Prev
    Next
    INDEX
    Explanations

    legal citations and similar references

    oai_token-act-pair · gemini-2.0-flash

    legal and mathematical references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ModelExpression
    -0.48
    ]")]
    -0.45
    ModelSerializer
    -0.44
     Unavailable
    -0.43
    XmlAccessType
    -0.42
    hout
    -0.42
    NEE
    -0.42
    不就是
    -0.42
    BrowserModule
    -0.41
     NUKAT
    -0.41
    POSITIVE LOGITS
     ProtoMessage
    0.92
    TagMode
    0.70
     Houſe
    0.66
    ArgsConstructor
    0.66
    Rptr
    0.63
     Generales
    0.63
    Šaltiniai
    0.61
    lapsingToolbar
    0.61
     honden
    0.60
     Majefty
    0.60
    Activations Density 0.796%

    No Known Activations