© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214841
    Prev
    Next
    INDEX
    Explanations

    row or line

    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
    ל
    1.44
    ل
    1.21
    یت
    1.20
    دید
    1.17
    ق
    1.10
    ید
    1.09
     दौरान
    1.09
    ﻟ
    1.09
    د
    1.06
     सवारी
    1.05
    POSITIVE LOGITS
    '
    1.41
    <0x80>
    1.40
    ing
    1.30
    ви
    1.21
    I
    1.20
    erver
    1.16
    0
    1.10
    ة
    1.07
    、
    1.05
    re
    1.05
    Activations Density 0.000%

    No Known Activations