© 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-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50317
    Prev
    Next
    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     außerdem
    0.44
     nato
    0.41
     mùi
    0.38
     deserialize
    0.38
     ਡ
    0.38
     viendo
    0.37
     ezek
    0.37
     جبکہ
    0.36
     didnt
    0.36
     ingrédients
    0.36
    POSITIVE LOGITS
    and
    0.41
    thanks
    0.41
    never
    0.40
    calcul
    0.40
    ront
    0.39
    \_
    0.38
    where
    0.37
    <0xC2>
    0.36
    راً
    0.36
    werden
    0.36
    Activations Density 0.010%

    No Known Activations