© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146658
    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
    3
    0.43
     Taban
    0.41
     Kupfer
    0.40
     Protok
    0.40
    Graphical
    0.38
     Graphical
    0.38
    Discrimin
    0.38
    9
    0.38
    Per
    0.37
     Manit
    0.37
    POSITIVE LOGITS
     out
    0.35
    checkpoint
    0.33
     tinge
    0.33
    出
    0.33
     reappear
    0.32
     raid
    0.32
    setDate
    0.32
    õe
    0.31
    wir
    0.31
    bate
    0.31
    Activations Density 0.000%

    No Known Activations