© 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
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 168122
    Prev
    Next
    INDEX
    Explanations

    harmful content and insults

    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_34_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
    ológicos
    0.40
    SP
    0.37
                                  
    0.37
    )(
    0.36
    〉
    0.35
    ѐ
    0.34
    ]').
    0.34
    or
    0.34
    particularly
    0.34
    樞
    0.33
    POSITIVE LOGITS
     fucking
    1.01
     shitty
    0.98
     fuck
    0.82
     Fuck
    0.82
     stupidity
    0.82
    Fuck
    0.82
     stupid
    0.79
     merda
    0.78
    fuck
    0.78
     fucked
    0.76
    Activations Density 0.167%

    No Known Activations