© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14429
    Prev
    Next
    INDEX
    Explanations

    admit or confess

    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_40_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
    ضای
    0.39
    idlertid
    0.39
     सित
    0.39
     Scam
    0.39
     Filtering
    0.38
    मूल
    0.37
     വള
    0.37
    優
    0.37
    סט
    0.36
     Belief
    0.35
    POSITIVE LOGITS
     admit
    1.47
     admitting
    1.43
     admitted
    1.38
     admits
    1.32
     Admit
    1.22
     confess
    1.21
    承认
    1.19
     confesses
    1.18
     confessed
    1.17
     admite
    1.11
    Activations Density 0.119%

    No Known Activations