© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261288
    Prev
    Next
    INDEX
    Explanations

    after view init or for loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    י
    1.40
    其他
    1.36
    し
    1.27
    ב
    1.26
    ل
    1.25
    ו
    1.24
    ي
    1.21
    т
    1.20
    л
    1.19
    ה
    1.15
    POSITIVE LOGITS
    N
    1.20
    O
    1.16
    I
    0.97
    Z
    0.96
    იდ
    0.95
    K
    0.91
    B
    0.91
    aris
    0.90
    Ns
    0.90
    C
    0.88
    Activations Density 0.000%

    No Known Activations