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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167717
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ็บ
    0.38
     supremely
    0.36
    膳
    0.35
    >(&
    0.33
     وكذلك
    0.33
     لمع
    0.33
     Nakam
    0.32
     insuring
    0.31
    🪐
    0.31
    localScale
    0.31
    POSITIVE LOGITS
    amask
    0.37
     빌
    0.36
     النهارده
    0.36
    ++);
    0.36
     バ
    0.34
    IVIDUAL
    0.34
    𒊒
    0.34
    க்குழு
    0.34
    ῆ
    0.34
    isieren
    0.34
    Activations Density 0.003%

    No Known Activations