© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80649
    Prev
    Next
    INDEX
    Explanations

    certificates

    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_0_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
    at
    2.16
    as
    2.06
    ل
    1.90
    on
    1.82
    و
    1.65
    en
    1.64
    ↵↵
    1.50
    the
    1.49
    ž
    1.45
    प
    1.44
    POSITIVE LOGITS
     تأثير
    1.43
     autochtones
    1.19
     pouvoirs
    1.19
     строки
    1.18
     студент
    1.17
     operandSize
    1.16
     нови
    1.14
     сде
    1.13
     своя
    1.13
     كامل
    1.10
    Activations Density 0.000%

    No Known Activations