© 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. 108750
    Prev
    Next
    INDEX
    Explanations

    Duke's Waikiki

    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
    :
    1.24
    ۴
    1.20
     on
    1.16
     thiab
    1.14
    5
    1.14
    ца
    1.07
     vacaciones
    1.07
    ς
    1.05
    ༤
    1.05
    ция
    1.04
    POSITIVE LOGITS
    p
    1.56
    b
    1.49
    v
    1.45
    al
    1.38
    id
    1.30
    f
    1.30
    ne
    1.22
    на
    1.20
    م
    1.13
    as
    1.09
    Activations Density 0.000%

    No Known Activations