© 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. 104136
    Prev
    Next
    INDEX
    Explanations

    improvisation or impulse related words

    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
    <0x0D>
    1.19
    O
    1.10
    ために
    1.06
    يات
    1.05
    نيا
    1.05
    fullName
    1.02
    PER
    1.01
     اين
    0.98
    ન
    0.96
    норийска
    0.94
    POSITIVE LOGITS
    er
    1.30
    ↵
    1.22
    р
    1.11
    an
    1.09
    .
    1.06
     more
    1.05
    м
    1.01
     their
    0.99
     very
    0.98
     necessary
    0.98
    Activations Density 0.000%

    No Known Activations