© 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. 199637
    Prev
    Next
    INDEX
    Explanations

    you followed by verb

    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
    läuft
    0.67
    ai
    0.63
    なります
    0.59
    都已经
    0.56
    oir
    0.55
    noons
    0.55
    fi
    0.54
    .";
    0.54
    ربية
    0.53
    de
    0.52
    POSITIVE LOGITS
     th
    0.63
    ות
    0.61
     ký
    0.61
    ස්ට
    0.61
    ၊
    0.61
    را
    0.60
     Optimize
    0.60
     ك
    0.59
     tarefa
    0.59
    碣
    0.59
    Activations Density 0.000%

    No Known Activations