© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206295
    Prev
    Next
    INDEX
    Explanations

    under the influence

    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_25_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
     Palmer
    0.48
    飏
    0.40
    Palmer
    0.40
     завтра
    0.39
    ména
    0.39
     Hume
    0.39
     Ripley
    0.39
    𝕞
    0.39
    ঁপ
    0.38
    멱
    0.38
    POSITIVE LOGITS
     valid
    0.43
     correctly
    0.42
    responding
    0.42
     responds
    0.41
     response
    0.40
    時の
    0.40
    さり
    0.40
    response
    0.40
     parsed
    0.40
     valido
    0.39
    Activations Density 0.000%

    No Known Activations