© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201222
    Prev
    Next
    INDEX
    Explanations

    below

    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_46_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
     narrow
    0.44
    INGER
    0.43
    Narrow
    0.43
    mersible
    0.40
     étroites
    0.40
    inger
    0.38
    mete
    0.38
    窄
    0.38
     Narrow
    0.38
    oció
    0.37
    POSITIVE LOGITS
    霊
    0.41
     मुस्क
    0.40
     Morph
    0.38
     hypogly
    0.37
     Gren
    0.36
     accurately
    0.36
     above
    0.36
     declaratory
    0.36
     عوض
    0.35
     morphine
    0.34
    Activations Density 0.003%

    No Known Activations