© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3477
    Prev
    Next
    INDEX
    Explanations

    wrong direction, location, order

    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
    र
    2.12
    ות
    2.10
    volving
    2.06
     incred
    1.99
    াবদ্ধ
    1.94
     edgecolor
    1.93
    iquement
    1.91
    nipeg
    1.91
    慄
    1.90
    ⎣
    1.86
    POSITIVE LOGITS
    я
    3.18
    т
    2.55
    ي
    2.45
    dır
    2.34
     나서
    2.30
     existir
    2.24
    ب
    2.22
    ح
    2.18
    стоит
    2.15
    ovane
    2.08
    Activations Density 0.000%

    No Known Activations