© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    quotations and the words 'said', 'says', 'tells', and 'added', as well as pronouns referring to the speaker, within them.

    oai_token-act-pair · gemini-2.0-flash

    saying

    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
    <bos>
    -0.60
     ब्रेकडाउन
    -0.49
    brainly
    -0.43
     Rouen
    -0.43
    ydd
    -0.43
    acha
    -0.43
    Mailer
    -0.43
    रीदारी
    -0.42
    PostInfinity
    -0.42
     Nich
    -0.42
    POSITIVE LOGITS
    istoitu
    0.47
     vulgaires
    0.45
    #+#
    0.45
    RenderAtEndOf
    0.42
     nahilalakip
    0.41
     suivants
    0.41
     MainAxisSize
    0.40
     blessé
    0.40
     utafitiHapana
    0.39
    Personendaten
    0.39
    Activations Density 1.722%

    No Known Activations