© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130654
    Prev
    Next
    INDEX
    Explanations

    names or titles following a general context

    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_6_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
    S
    0.94
    RS
    0.92
    "،
    0.91
    ности
    0.89
    меч
    0.89
     sanitizer
    0.88
    ли
    0.87
    ст
    0.86
    )،
    0.86
    R
    0.86
    POSITIVE LOGITS
    ı
    0.95
    <0xA8>
    0.89
    <0x80>
    0.76
     Wasn
    0.75
    for
    0.73
    inating
    0.71
    ong
    0.70
    isn
    0.70
    atam
    0.67
    <0x91>
    0.66
    Activations Density 0.017%

    No Known Activations