© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90901
    Prev
    Next
    INDEX
    Explanations

    "Val" prefixes and suffixes

    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_3_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
    ule
    0.76
    रि
    0.73
    ή
    0.70
    gj
    0.67
    রা
    0.66
     वैदिक
    0.66
    ow
    0.65
    pf
    0.64
    g
    0.63
    me
    0.61
    POSITIVE LOGITS
    an
    0.82
    er
    0.74
    \
    0.70
    的问题
    0.65
    ي
    0.64
    িশালী
    0.60
    েন
    0.60
     канди
    0.59
    tela
    0.59
    től
    0.59
    Activations Density 0.003%

    No Known Activations