© 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. 83143
    Prev
    Next
    INDEX
    Explanations

    river crossings or entering rivers

    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
    '
    1.41
    ur
    1.15
    ing
    1.09
     affective
    1.09
    us
    1.07
    มะ
    1.04
    izability
    1.02
    isation
    1.00
    ués
    0.98
    ajou
    0.97
    POSITIVE LOGITS
    י
    1.77
    O
    1.55
    ли
    1.49
    ی
    1.48
    т
    1.47
     on
    1.46
    س
    1.46
    U
    1.45
    .}
    1.44
     with
    1.43
    Activations Density 0.000%

    No Known Activations