© 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. 167719
    Prev
    Next
    INDEX
    Explanations

    <

    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
     Funktionen
    0.41
     (--
    0.39
     MinMaxScaler
    0.38
     enjoys
    0.37
    ANDA
    0.37
    rystalline
    0.37
     marries
    0.37
     fulfils
    0.37
     rapid
    0.37
    過去
    0.36
    POSITIVE LOGITS
    fast
    0.54
    Fast
    0.48
    Nes
    0.45
     fast
    0.44
    FAST
    0.43
    快
    0.42
    gl
    0.42
    Ste
    0.42
     फास्ट
    0.42
    Fre
    0.41
    Activations Density 0.000%

    No Known Activations