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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105985
    Prev
    Next
    INDEX
    Explanations

    BOX rests

    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_1_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
    ي
    1.69
    ко
    1.60
    ни
    1.51
    ون
    1.50
    as
    1.39
    та
    1.39
    ش
    1.35
    াম
    1.31
    า
    1.30
    an
    1.30
    POSITIVE LOGITS
    <bos>
    1.63
    ography
    1.20
     it
    1.16
    worthiness
    1.13
                         
    1.03
     $\
    1.01
    isode
    1.01
     }^{+}$
    1.00
     ﺍﻟ
    0.99
    kc
    0.98
    Activations Density 0.000%

    No Known Activations