© 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. 205876
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ':
    0.45
    ":
    0.42
    {{
    0.38
    Jou
    0.37
    quent
    0.37
    SIGN
    0.36
    JUN
    0.36
    piece
    0.36
    THRESH
    0.36
    Article
    0.35
    POSITIVE LOGITS
    ）』
    0.38
    发挥
    0.37
     &__
    0.37
     Shet
    0.37
     Batista
    0.36
    力を
    0.36
    力
    0.36
     Nunes
    0.36
    踮
    0.36
     extant
    0.35
    Activations Density 0.006%

    No Known Activations