Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167380
    Prev
    Next
    INDEX
    Explanations

    addresses and places

    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
     задума
    0.38
    ᒪ
    0.37
     Substances
    0.36
    އް
    0.35
    لاميذ
    0.35
    たたみ
    0.34
    POINT
    0.34
     दिशा
    0.34
     веществ
    0.34
    তথ্য
    0.33
    POSITIVE LOGITS
     ob
    0.39
     Advers
    0.38
    世
    0.37
     Lent
    0.37
    𒄩
    0.37
     uz
    0.36
     Hit
    0.36
     Nielsen
    0.35
     శ్రీ
    0.35
     adversarial
    0.35
    Activations Density 0.000%

    No Known Activations