© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201546
    Prev
    Next
    INDEX
    Explanations

    implementation

    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_12_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
    ره
    0.50
    يكي
    0.49
     История
    0.49
     pengambilan
    0.48
    文
    0.48
     decimated
    0.48
    𝐲
    0.47
     Printers
    0.47
     বিগ
    0.46
    у
    0.46
    POSITIVE LOGITS
    can
    0.50
     luxe
    0.50
     extends
    0.50
    safe
    0.49
    cit
    0.49
    src
    0.49
    alten
    0.48
    acte
    0.47
    cel
    0.46
    äv
    0.46
    Activations Density 0.000%

    No Known Activations