© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9193
    Prev
    Next
    INDEX
    Explanations

    language comparing the cost or process of buying vs. making something, particularly clothes.

    oai_token-act-pair · gemini-2.0-flash

    buy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     unknownFields
    -0.74
     للمعارف
    -0.71
     مرئيه
    -0.71
    Архівовано
    -0.71
     ModelExpression
    -0.69
    #+#
    -0.65
     protoimpl
    -0.60
    tagext
    -0.60
     оригіналу
    -0.57
     onCreateView
    -0.56
    POSITIVE LOGITS
     ögon
    0.53
    NewGuid
    0.52
     bakgrund
    0.45
    طان
    0.45
    INCREF
    0.45
    msgSender
    0.45
     Unidas
    0.44
    cution
    0.42
    ciuto
    0.42
     fund
    0.41
    Activations Density 0.538%

    No Known Activations