© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9687
    Prev
    Next
    INDEX
    Explanations

    tables comparing features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    1.41
    í
    1.27
    us
    1.20
    ost
    1.20
    upon
    1.14
    ir
    1.12
    ère
    1.10
    il
    1.07
    og
    1.07
    ie
    1.07
    POSITIVE LOGITS
    ਗ
    1.33
     қили
    1.32
    ш
    1.24
    ALLED
    1.23
    IZING
    1.23
    ে
    1.23
    ADOS
    1.22
    IDES
    1.20
    AMSUNG
    1.16
    েও
    1.15
    Activations Density 0.005%

    No Known Activations