© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151434
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     house
    0.82
     House
    0.80
    House
    0.72
     haus
    0.72
     HOUSE
    0.69
     হাউস
    0.64
    house
    0.64
     집
    0.63
     Houses
    0.63
     дом
    0.62
    POSITIVE LOGITS
    Down
    0.76
     down
    0.71
     eigene
    0.70
    Own
    0.68
     Down
    0.66
     DOWN
    0.65
     włas
    0.64
    down
    0.63
     डाउन
    0.62
    ลง
    0.62
    Activations Density 0.000%

    No Known Activations