© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69020
    Prev
    Next
    INDEX
    Explanations

    sounds/words

    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_51_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
    َى
    0.43
    <h6>
    0.41
    ിയ
    0.41
    yap
    0.40
    yenne
    0.39
    ʸ
    0.39
     निकाली
    0.38
    ueve
    0.38
     marm
    0.38
    յ
    0.37
    POSITIVE LOGITS
    amu
    0.51
     Amend
    0.46
    amil
    0.46
    amen
    0.46
     الأمن
    0.44
     amen
    0.43
    abit
    0.42
    amid
    0.41
    চ্ছন্দ
    0.41
     amel
    0.41
    Activations Density 0.000%

    No Known Activations