© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52767
    Prev
    Next
    INDEX
    Explanations

    read carefully

    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
    SEE
    0.38
    pile
    0.37
    wl
    0.35
    ന്ത്രാ
    0.35
    鍋
    0.35
     Nils
    0.35
     Argos
    0.34
     представляют
    0.34
    qal
    0.33
     Wrangler
    0.33
    POSITIVE LOGITS
    ALLY
    0.40
     ergonom
    0.38
     QUANT
    0.38
    erat
    0.38
     SOP
    0.37
     Numeric
    0.37
    Ỡ
    0.37
     EMPLOY
    0.37
    ｼ
    0.37
     UINT
    0.37
    Activations Density 0.002%

    No Known Activations