© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246275
    Prev
    Next
    INDEX
    Explanations

    numbers and specific characters

    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_40_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
     Iron
    0.43
     iron
    0.42
     Forty
    0.42
     Foam
    0.41
     Snow
    0.41
    邰
    0.41
     besi
    0.40
    拏
    0.40
     prel
    0.39
     snowy
    0.38
    POSITIVE LOGITS
     sbParams
    0.41
    
    0.37
     documental
    0.36
    geg
    0.36
    executable
    0.36
     ஏதாவது
    0.36
     документа
    0.36
    উ
    0.36
     দলিল
    0.35
    lois
    0.35
    Activations Density 0.010%

    No Known Activations