© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106156
    Prev
    Next
    INDEX
    Explanations

    basic followed by rights or services

    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_1_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
    :
    1.91
    un
    1.30
    ay
    1.22
    5
    1.20
    の
    1.19
     merda
    1.12
    8
    1.12
    7
    1.09
    4
    1.09
    وم
    1.06
    POSITIVE LOGITS
    <0x80>
    1.38
    t
    0.99
    ized
    0.95
    ant
    0.94
    fat
    0.93
    ths
    0.92
    0
    0.90
    truck
    0.89
    rei
    0.89
    fing
    0.89
    Activations Density 0.004%

    No Known Activations