© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198296
    Prev
    Next
    INDEX
    Explanations

    seriousness of crime or offense

    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_12_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
    )
    0.68
     ዘዴ
    0.64
    ;
    0.61
    }
    0.60
    ]
    0.59
     Arz
    0.59
    ),
    0.58
    Electronic
    0.56
     خير
    0.56
     बजर
    0.55
    POSITIVE LOGITS
    ｐ
    0.58
    ８
    0.56
     seriousness
    0.54
    凝
    0.53
    Ｇ
    0.50
    وں
    0.49
    infection
    0.46
    ｖ
    0.45
    <0xB2>
    0.45
    theta
    0.44
    Activations Density 0.002%

    No Known Activations