© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66444
    Prev
    Next
    INDEX
    Explanations

    received acceptance or diagnosis

    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_41_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
    icide
    0.65
     Killing
    0.62
     killing
    0.59
     Kill
    0.57
     kill
    0.54
    殺
    0.49
     murdering
    0.49
    杀死
    0.49
    icides
    0.48
    弑
    0.48
    POSITIVE LOGITS
     received
    1.21
    received
    1.09
    receive
    1.07
    Receive
    1.06
     receive
    1.04
    Received
    1.04
     recibir
    1.03
     receb
    1.03
     Received
    1.02
     receiving
    1.02
    Activations Density 0.093%

    No Known Activations