© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138218
    Prev
    Next
    INDEX
    Explanations

    certainty of death or loss

    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
    is
    0.47
    are
    0.45
    Ht
    0.42
    ie
    0.42
    oke
    0.41
    5
    0.41
    ığında
    0.41
     मिळते
    0.41
    4
    0.41
    webhook
    0.41
    POSITIVE LOGITS
     Schwann
    0.55
     Slice
    0.53
     SMEs
    0.50
    كي
    0.50
     concedes
    0.48
    и
    0.48
    کي
    0.46
     И
    0.46
     conceding
    0.46
     Си
    0.45
    Activations Density 0.000%

    No Known Activations