© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31242
    Prev
    Next
    INDEX
    Explanations

    key

    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_50_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
     ግራም
    0.43
     frå
    0.43
     Diverse
    0.42
     tady
    0.42
    攢
    0.41
     предприя
    0.40
    Holds
    0.39
    غيل
    0.39
     تۆ
    0.39
    গির
    0.39
    POSITIVE LOGITS
     nick
    0.36
     cars
    0.36
     fuck
    0.35
    substack
    0.35
    luc
    0.35
    \{
    0.34
    \{(
    0.34
     cracking
    0.34
     fro
    0.34
     fluxes
    0.33
    Activations Density 0.000%

    No Known Activations