© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196736
    Prev
    Next
    INDEX
    Explanations

    et al

    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_15_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
     Deduction
    0.54
    m
    0.53
    <0x0D>
    0.49
     Cooling
    0.46
     Anfang
    0.46
     Bernoulli
    0.45
     Preventing
    0.44
     Letting
    0.44
     Kelas
    0.44
     Kimura
    0.43
    POSITIVE LOGITS
    <unused506>
    0.58
    _/
    0.57
    geschichte
    0.55
     خاک
    0.54
     publish
    0.53
     campfire
    0.51
     "../../
    0.51
     vibhav
    0.50
    ISPW
    0.50
    เจน
    0.50
    Activations Density 0.000%

    No Known Activations