© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116307
    Prev
    Next
    INDEX
    Explanations

    AWS, an, paper, The, A, Two, Modern

    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_27_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
    \
    0.33
     Colegio
    0.32
     planes
    0.32
     alma
    0.31
     Funktion
    0.31
    হীন
    0.31
    iculares
    0.31
    pillar
    0.30
     feel
    0.29
     almac
    0.29
    POSITIVE LOGITS
    銖
    0.34
    নান
    0.34
     ચૂ
    0.33
    அத
    0.33
     काटकर
    0.32
     чере
    0.32
    螭
    0.32
     በጥ
    0.32
    ולי
    0.31
     விழு
    0.30
    Activations Density 0.010%

    No Known Activations