© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228756
    Prev
    Next
    INDEX
    Explanations

    say ")"

    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
     यांना
    0.42
    ']:
    0.40
    タ
    0.39
    ')+
    0.39
     pptd
    0.38
    _{+}+
    0.36
    ])+
    0.36
     wyt
    0.36
    enziali
    0.36
    ',{
    0.36
    POSITIVE LOGITS
     number
    0.41
     unheard
    0.40
     ceremonial
    0.40
     im
    0.39
     prolonged
    0.39
     voucher
    0.39
     infinite
    0.38
     symbolic
    0.38
     hool
    0.38
     five
    0.37
    Activations Density 0.010%

    No Known Activations