© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    words related to deep investigation and specifics.

    oai_token-act-pair · gemini-2.0-flash

    detail

    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
     detail
    -1.66
     Detail
    -1.63
     details
    -1.58
    detail
    -1.48
    Detail
    -1.48
     DETAIL
    -1.42
     Details
    -1.41
    details
    -1.40
    DETAIL
    -1.32
    Details
    -1.30
    POSITIVE LOGITS
    EDEFAULT
    0.58
     quí
    0.48
    class
    0.47
    lippe
    0.47
    ГЛА
    0.45
    觅
    0.45
    Class
    0.44
     recognized
    0.44
     Weiner
    0.44
     cổ
    0.44
    Activations Density 34.017%

    No Known Activations