© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87254
    Prev
    Next
    INDEX
    Explanations

    Rayleigh scattering, desiccation, Piazza

    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_3_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
    I
    0.92
    A
    0.80
    (
    0.70
    Ⲏ
    0.66
    Ве
    0.64
    se
    0.63
    ו
    0.63
    ፩
    0.63
    ngram
    0.62
    de
    0.61
    POSITIVE LOGITS
    ERRY
    0.69
     partido
    0.68
     agua
    0.66
     technologie
    0.66
     leren
    0.64
    ol
    0.63
     informatie
    0.63
    aire
    0.63
    ুল
    0.61
    aan
    0.61
    Activations Density 0.000%

    No Known Activations