© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88891
    Prev
    Next
    INDEX
    Explanations

    detoxification and germination

    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_23_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
    Security
    0.42
    Bi
    0.41
    🙏🙏
    0.41
    Plus
    0.40
    ()+
    0.39
     bunk
    0.38
    Bad
    0.38
    +
    0.38
    ског
    0.38
    साठी
    0.37
    POSITIVE LOGITS
    整数
    0.41
    ้าม
    0.38
     математи
    0.38
    値を
    0.38
    属于
    0.38
    段階
    0.37
     mathematic
    0.37
    ᖁ
    0.37
    屬於
    0.36
     Encyclop
    0.36
    Activations Density 0.000%

    No Known Activations