© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3570
    Prev
    Next
    INDEX
    Explanations

    low and slow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     واست
    1.00
    ោះស្រាយ
    0.99
    ambito
    0.99
    ać
    0.97
     فين
    0.95
    <unused131>
    0.94
     Â
    0.94
    }$
    0.94
     â
    0.92
    defini
    0.92
    POSITIVE LOGITS
     equivariant
    1.15
    waitTime
    1.13
    স
    1.09
    isPrime
    1.08
    нің
    1.04
    कर
    1.03
    Одно
    0.99
     brows
    0.98
     সপ্ত
    0.96
    nown
    0.96
    Activations Density 0.001%

    No Known Activations