© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253141
    Prev
    Next
    INDEX
    Explanations

    chrom

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    '[
    0.39
     هار
    0.38
    웬
    0.38
     hert
    0.36
    derivative
    0.35
    ViewModels
    0.35
    Ꮝ
    0.34
    mesi
    0.34
    集成
    0.33
     मजि
    0.33
    POSITIVE LOGITS
    atically
    0.47
     New
    0.45
    ína
    0.43
    s
    0.41
     Key
    0.40
    AB
    0.40
    atics
    0.39
    ATIC
    0.39
    amak
    0.38
    iação
    0.38
    Activations Density 0.001%

    No Known Activations