© 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. 77109
    Prev
    Next
    INDEX
    Explanations

    Louis

    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
     faintly
    0.39
     trivial
    0.37
     artery
    0.36
     subconsciously
    0.35
    匪
    0.35
     shilling
    0.35
    triggers
    0.34
     मौजूदगी
    0.34
    okban
    0.34
     arteries
    0.34
    POSITIVE LOGITS
     Startup
    0.42
     please
    0.40
     Mould
    0.40
     Today
    0.39
    脨
    0.38
    ತ್ತ
    0.37
     Craft
    0.37
     Durable
    0.36
    终于
    0.36
     наконец
    0.36
    Activations Density 0.000%

    No Known Activations