© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133233
    Prev
    Next
    INDEX
    Explanations

    mutators and transmutation

    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_6_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
    지는
    1.23
    스의
    1.05
    л
    1.05
    나
    1.02
    스는
    1.00
    lığ
    0.98
     industria
    0.96
     pSig
    0.96
    ון
    0.95
    ウス
    0.95
    POSITIVE LOGITS
    ed
    1.86
    ing
    1.80
    og
    1.77
    n
    1.48
    ic
    1.46
    oc
    1.46
    at
    1.43
    ee
    1.38
    h
    1.37
    a
    1.36
    Activations Density 0.001%

    No Known Activations