© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250745
    Prev
    Next
    INDEX
    Explanations

    labels

    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
    PTH
    0.45
     Pay
    0.41
     sparsim
    0.41
     Drew
    0.39
     Наи
    0.39
    糇
    0.39
     najbol
    0.38
     कार्यों
    0.38
    کاری
    0.38
     Anal
    0.38
    POSITIVE LOGITS
     end
    0.53
     inter
    0.51
    Inter
    0.46
     Inter
    0.45
    De
    0.43
     ré
    0.43
     데
    0.42
    su
    0.41
     cred
    0.41
     Deccan
    0.40
    Activations Density 0.012%

    No Known Activations