© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45262
    Prev
    Next
    INDEX
    Explanations

    privacy policy

    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_3_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
    mag
    0.64
     অভাব
    0.64
    haven
    0.61
    psych
    0.58
    problem
    0.58
    Exactly
    0.57
    information
    0.57
    ]
    0.57
    ud
    0.56
    profitable
    0.56
    POSITIVE LOGITS
    ą
    0.71
    ER
    0.65
     svě
    0.62
     fă
    0.60
    ي
    0.60
     protrusions
    0.60
     shadowy
    0.60
    队
    0.59
     pade
    0.57
    in
    0.57
    Activations Density 0.000%

    No Known Activations