© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 800
    Prev
    Next
    INDEX
    Explanations

    code definition delimiters

    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_40_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
     बनते
    0.40
     러
    0.38
     Liên
    0.38
    કે
    0.38
    ępu
    0.38
    руса
    0.38
    férence
    0.37
     vaults
    0.37
     रिप्रे
    0.37
    𒊑
    0.36
    POSITIVE LOGITS
     সঞ্চ
    0.40
     дево
    0.38
     descriptive
    0.36
     деву
    0.36
    ystycz
    0.36
     obscurity
    0.35
    Hour
    0.34
    经常
    0.34
    Catch
    0.34
     часто
    0.34
    Activations Density 0.026%

    No Known Activations