© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52276
    Prev
    Next
    INDEX
    Explanations

    code command

    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_30_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
     sad
    0.35
    Sad
    0.35
    ”
    0.34
    word
    0.34
    </
    0.34
     отношение
    0.33
     hairline
    0.33
     Sad
    0.33
    <b>
    0.32
    \"
    0.32
    POSITIVE LOGITS
    ായത്
    0.42
     estructura
    0.41
    ૃત
    0.41
    ቻል
    0.41
     शुर
    0.40
    ريض
    0.39
    瘪
    0.39
     デ
    0.39
     élargies
    0.39
     домаћинства
    0.39
    Activations Density 0.000%

    No Known Activations