© 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. 83595
    Prev
    Next
    INDEX
    Explanations

    harvest

    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
    '
    1.64
    سي
    1.48
    ه
    1.48
    "
    1.44
    يها
    1.41
    ată
    1.38
    عرف
    1.31
    nimmt
    1.31
    تي
    1.30
    ת
    1.28
    POSITIVE LOGITS
    are
    1.29
     heterocyclic
    1.19
    ique
    1.18
    ī
    1.16
    ile
    1.13
    ah
    1.13
    रा
    1.13
    uh
    1.12
    ö
    1.12
    un
    1.11
    Activations Density 0.000%

    No Known Activations