© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58177
    Prev
    Next
    INDEX
    Explanations

    pro words and prow words

    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_2_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
    し
    1.76
    с
    1.60
    ться
    1.36
    จะ
    1.34
    ama
    1.32
    ї
    1.30
    ных
    1.30
    we
    1.24
    માં
    1.22
    ш
    1.22
    POSITIVE LOGITS
    ↵
    1.15
     encouraged
    1.08
     forefathers
    1.00
     presses
    0.98
    AB
    0.98
     L
    0.97
     presets
    0.97
     loafers
    0.96
    ähler
    0.95
     progenitors
    0.94
    Activations Density 0.000%

    No Known Activations