© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207000
    Prev
    Next
    INDEX
    Explanations

    automated

    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
     =
    0.35
     kaç
    0.33
     :=
    0.31
     hingga
    0.30
     lor
    0.30
     és
    0.30
     Vectors
    0.30
     be
    0.29
    :=
    0.29
     ២
    0.29
    POSITIVE LOGITS
    Ꮸ
    0.31
    তান্ত্রিক
    0.30
    Metric
    0.29
    puff
    0.29
    তই
    0.28
    दया
    0.27
    reel
    0.27
    Gust
    0.27
    Chang
    0.27
     Archim
    0.27
    Activations Density 0.007%

    No Known Activations