© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78621
    Prev
    Next
    INDEX
    Explanations

    using

    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_0_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
    AR
    1.47
    )
    1.34
    :
    1.21
    );
    1.20
    ER
    1.13
    O
    1.13
    AB
    1.13
        
    1.11
    OL
    1.10
    Have
    1.10
    POSITIVE LOGITS
    на
    1.66
    ری
    1.61
    ال
    1.30
     در
    1.30
    p
    1.30
    لی
    1.22
    ль
    1.20
    াল
    1.20
    も含
    1.16
    c
    1.16
    Activations Density 0.021%

    No Known Activations