© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117527
    Prev
    Next
    INDEX
    Explanations

    factoring out variable

    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_27_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
    गुरु
    0.40
     Beyer
    0.38
     alış
    0.37
    prese
    0.37
    igue
    0.37
     аро
    0.37
    騾
    0.36
    Detroit
    0.36
    MIX
    0.35
     Don
    0.35
    POSITIVE LOGITS
    나무
    0.35
    HttpPut
    0.35
    ँकि
    0.34
    =',')
    0.34
     уйна
    0.33
    ត
    0.33
    Chúc
    0.33
     trouvait
    0.33
    夰
    0.33
    δικ
    0.32
    Activations Density 0.001%

    No Known Activations