© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 167984
    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_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
     UST
    0.43
     UF
    0.43
     UID
    0.43
     UCF
    0.41
    ጃ
    0.40
     UC
    0.40
     UCS
    0.40
     ULTRA
    0.39
     UT
    0.39
     PF
    0.38
    POSITIVE LOGITS
    """,
    0.43
     few
    0.40
    ron
    0.40
    ;',
    0.39
    皘
    0.37
     finely
    0.35
    ktiv
    0.35
     scenic
    0.35
     nice
    0.35
    ACB
    0.35
    Activations Density 0.000%

    No Known Activations