© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85336
    Prev
    Next
    INDEX
    Explanations

    called once, called before

    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_23_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
    CHAP
    0.41
     notwithstanding
    0.39
     subsequently
    0.39
     chew
    0.38
    ECH
    0.38
    เพิ่มเติม
    0.37
    結果
    0.37
    N
    0.36
    Taylor
    0.36
    Flow
    0.36
    POSITIVE LOGITS
     /></
    0.43
     டாக்டர்
    0.41
    ቭ
    0.40
     Horticultural
    0.40
     финансовых
    0.39
     Physician
    0.39
     gamme
    0.38
     socialista
    0.38
     phía
    0.38
     gama
    0.38
    Activations Density 0.000%

    No Known Activations