© 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. 210381
    Prev
    Next
    INDEX
    Explanations

    wanna + verb

    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
    is
    1.38
    to
    1.26
    ко
    1.25
    ен
    1.23
    ер
    1.15
    é
    1.10
    ো
    1.02
    on
    1.00
    um
    1.00
    ar
    0.98
    POSITIVE LOGITS
     at
    1.46
    ק
    1.09
    ס
    1.03
    f
    1.02
     are
    1.01
    க்
    1.01
    ]
    1.00
    ರೆ
    0.99
    ac
    0.98
    )$.
    0.98
    Activations Density 0.000%

    No Known Activations