© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167141
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful content

    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_31_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
     bek
    0.43
     Pud
    0.42
     pund
    0.37
     pudding
    0.37
    槛
    0.36
     മു
    0.36
     mez
    0.36
     pedestrian
    0.36
     kelu
    0.36
    ুরুর
    0.36
    POSITIVE LOGITS
    SERT
    0.40
    Lion
    0.40
    Servo
    0.40
    Without
    0.38
    ানিতে
    0.38
     showcased
    0.35
     Großbritannien
    0.35
     لديها
    0.35
    Inch
    0.35
    🌝
    0.35
    Activations Density 0.000%

    No Known Activations