© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18677
    Prev
    Next
    INDEX
    Explanations

    balance factor in trees

    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_40_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
     Bridg
    0.43
    တင်
    0.40
    👏👏👏👏
    0.39
    👏👏
    0.39
    🫰
    0.39
    बैंड
    0.38
     तैनात
    0.38
    cled
    0.38
    ราะห์
    0.38
    蕴
    0.38
    POSITIVE LOGITS
     factor
    0.42
    Factor
    0.40
     fuori
    0.39
     ASI
    0.37
     speed
    0.35
    feels
    0.35
     everyone
    0.35
    speed
    0.35
    Loop
    0.35
    grouped
    0.35
    Activations Density 0.001%

    No Known Activations