© 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. 103249
    Prev
    Next
    INDEX
    Explanations

    jingle or shingle

    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
    <0x80>
    1.27
    >
    1.18
     have
    1.09
    '
    1.08
     be
    0.92
     demarc
    0.91
    ),
    0.90
     don
    0.88
    າມາດ
    0.87
     romantic
    0.86
    POSITIVE LOGITS
    .
    1.33
    在
    1.30
    na
    1.21
    8
    1.18
    ন
    1.14
    6
    1.13
    3
    1.13
    ين
    1.08
    К
    1.08
    ne
    1.07
    Activations Density 0.000%

    No Known Activations