© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45684
    Prev
    Next
    INDEX
    Explanations

    EleutherAI or names ending in -thymis

    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_3_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
    я
    1.13
    ী
    1.09
    न
    1.06
    r
    0.98
    િ
    0.96
    ק
    0.84
    어
    0.83
    ת
    0.82
    ين
    0.81
    મ
    0.81
    POSITIVE LOGITS
    am
    0.96
    at
    0.85
    as
    0.77
    to
    0.74
    的
    0.72
    ppes
    0.71
    ved
    0.70
    ledge
    0.70
    acks
    0.70
    ppin
    0.70
    Activations Density 0.000%

    No Known Activations