© 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-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109074
    Prev
    Next
    INDEX
    Explanations

    ELK Stack or elk animal

    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_2_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
    (
    1.98
    us
    1.55
    AG
    1.37
    and
    1.34
    ing
    1.32
    ة
    1.29
    '
    1.22
    ک
    1.16
    علام
    1.15
    (.*
    1.13
    POSITIVE LOGITS
    the
    1.20
    ր
    1.09
     disorganized
    1.08
    ных
    0.99
    ır
    0.98
    ного
    0.90
    मस
    0.89
     presion
    0.88
    㶲
    0.88
     veineux
    0.88
    Activations Density 0.000%

    No Known Activations