© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210662
    Prev
    Next
    INDEX
    Explanations

    access modifiers

    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_43_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
     kembali
    0.41
    ambe
    0.39
    restore
    0.38
    再一次
    0.38
    戻
    0.38
    再次
    0.37
     AGAIN
    0.37
    密切
    0.37
     tracksuit
    0.37
    ્રી
    0.36
    POSITIVE LOGITS
    νομα
    0.44
     Swo
    0.36
    нення
    0.36
    ブレ
    0.36
     Tokens
    0.35
     token
    0.35
     ታ
    0.35
     á
    0.34
     Token
    0.34
     minimo
    0.34
    Activations Density 0.000%

    No Known Activations