© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107953
    Prev
    Next
    INDEX
    Explanations

    towel or vowel sounds

    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_1_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
    to
    1.68
     to
    1.41
    0
    1.24
     can
    1.16
    ta
    1.13
     was
    1.09
    на
    1.05
     。,
    1.02
     on
    0.99
    UM
    0.99
    POSITIVE LOGITS
    ми
    1.27
     paradigms
    1.16
    و
    1.16
    ors
    1.09
    ۳
    1.05
    ot
    1.02
    emples
    0.98
    inuation
    0.95
    ellers
    0.94
    jeni
    0.94
    Activations Density 0.000%

    No Known Activations