© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80105
    Prev
    Next
    INDEX
    Explanations

    currency symbols followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ety
    0.41
    elij
    0.38
    =_
    0.38
    omon
    0.37
    wd
    0.36
    uj
    0.36
    igen
    0.36
    gada
    0.36
    鳗
    0.36
    idades
    0.36
    POSITIVE LOGITS
     DISCUSSION
    0.40
     GP
    0.37
     CYP
    0.37
     GPs
    0.37
     unloading
    0.36
    âni
    0.35
     action
    0.35
     regrowth
    0.35
     BM
    0.35
     Bankruptcy
    0.34
    Activations Density 0.001%

    No Known Activations