© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126000
    Prev
    Next
    INDEX
    Explanations

    PBKDF2 or PCB, PKK

    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
    ле
    0.73
     cataly
    0.71
     pusieron
    0.68
    -
    0.67
    ബ
    0.66
     provoque
    0.65
    ס
    0.63
    ർ
    0.62
     marcha
    0.62
     podej
    0.62
    POSITIVE LOGITS
     or
    0.90
    AT
    0.77
    X
    0.74
    ın
    0.70
    rün
    0.67
    OL
    0.64
    ক
    0.64
    I
    0.64
    ENDMENT
    0.63
    و
    0.62
    Activations Density 0.000%

    No Known Activations