© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100921
    Prev
    Next
    INDEX
    Explanations

    battles, recommends, events, theme, generous, Hispanic

    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_16_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
    reform
    0.58
    2
    0.52
    መም
    0.50
    sp
    0.50
    gget
    0.49
     ഒരിക്ക
    0.48
    psy
    0.47
    lej
    0.47
    do
    0.45
    normalization
    0.45
    POSITIVE LOGITS
     собрать
    0.45
     alterations
    0.44
     ות
    0.44
     ligados
    0.44
     (
    0.43
    ッド
    0.43
     או
    0.42
     ode
    0.42
     shampoos
    0.42
     ও
    0.41
    Activations Density 0.000%

    No Known Activations