© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218185
    Prev
    Next
    INDEX
    Explanations

    official entities

    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_47_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
    rightarrow
    0.39
     bege
    0.39
     regulator
    0.38
     BOP
    0.38
     Regulator
    0.37
     regulators
    0.37
    渭
    0.37
     गांधी
    0.36
    cartes
    0.35
     Signals
    0.35
    POSITIVE LOGITS
    Dialogue
    0.42
    筠
    0.41
    <iframe>
    0.38
     स
    0.38
     꼭
    0.38
    стье
    0.38
    벼
    0.38
    rib
    0.37
    nero
    0.37
     kra
    0.37
    Activations Density 0.000%

    No Known Activations