© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48707
    Prev
    Next
    INDEX
    Explanations

    delimiters or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    sof
    0.40
     Telegram
    0.39
    jud
    0.39
     drawing
    0.38
    ]),
    0.37
    Telegram
    0.37
    ˈ
    0.35
     KA
    0.35
    wert
    0.35
     traffic
    0.35
    POSITIVE LOGITS
     espaços
    0.43
     espacios
    0.42
    Spaces
    0.40
     delimiters
    0.40
    ñada
    0.38
     delimiter
    0.38
    スペース
    0.38
     spaces
    0.37
     শূ
    0.37
     spazi
    0.36
    Activations Density 0.008%

    No Known Activations