© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51804
    Prev
    Next
    INDEX
    Explanations

    death and life

    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_31_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
    insured
    0.42
    abilité
    0.39
    friendly
    0.38
    ামি
    0.38
    刧
    0.38
    矚
    0.37
    ۆی
    0.36
    inputValue
    0.36
    APY
    0.36
     friendly
    0.35
    POSITIVE LOGITS
     সুভাষ
    0.38
    ндары
    0.38
    三人
    0.37
     computeEncoder
    0.36
     গভীরভাবে
    0.36
    伀
    0.36
    idene
    0.36
    ெமி
    0.36
    财
    0.35
     ومن
    0.35
    Activations Density 0.000%

    No Known Activations