© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     an
    0.42
    {
    0.41
     catatan
    0.40
     alters
    0.39
     LOWER
    0.39
     стиль
    0.39
     altered
    0.37
     fault
    0.37
     cross
    0.37
     lives
    0.37
    POSITIVE LOGITS
     .)
    0.51
     .”
    0.47
    Ob
    0.46
     ."
    0.44
     .'
    0.43
    Mob
    0.41
    O
    0.41
    ★★
    0.40
    Stra
    0.40
    Sid
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.