© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157989
    Prev
    Next
    INDEX
    Explanations

    tuba toothpaste / masturbation

    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_2_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
    (
    1.67
    as
    1.36
    t
    1.29
    -
    1.24
    ية
    1.22
    á
    1.21
     be
    1.20
    م
    1.19
    ž
    1.15
    고
    1.15
    POSITIVE LOGITS
    ی
    1.18
     executed
    1.09
    ი
    1.07
    ન
    1.07
     accuses
    1.04
    ０
    1.02
     アイ
    1.01
    ের
    1.00
    ак
    1.00
     otor
    1.00
    Activations Density 0.000%

    No Known Activations