© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107740
    Prev
    Next
    INDEX
    Explanations

    enables systems, developers, tracking, processing, navigation, illegal activities, digital functionality

    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_2_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
    in
    1.69
    ’
    1.66
    s
    1.49
    I
    1.35
    q
    1.34
    to
    1.31
    <0x0D>
    1.25
    on
    1.22
    ’)
    1.22
                    
    1.21
    POSITIVE LOGITS
    ре
    1.19
    ل
    1.16
    ח
    1.14
    లు
    1.09
    ری
    1.09
    zinho
    1.08
    ू
    1.07
    ロ
    1.05
     invigorating
    1.04
     overflowing
    1.03
    Activations Density 0.001%

    No Known Activations