© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229187
    Prev
    Next
    INDEX
    Explanations

    tener

    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_57_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
     anterior
    0.49
     Anterior
    0.45
    mények
    0.41
    LECT
    0.40
    琕
    0.40
    rokken
    0.39
    anterior
    0.38
     antérieurs
    0.38
    SEY
    0.38
     ஆண்க
    0.38
    POSITIVE LOGITS
    임
    0.40
    Tod
    0.39
    tod
    0.39
    渇
    0.39
     tod
    0.39
     asp
    0.36
     rec
    0.35
    lay
    0.35
     коп
    0.35
     Tomcat
    0.34
    Activations Density 0.001%

    No Known Activations