© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13514
    Prev
    Next
    INDEX
    Explanations

    age ranges 30s-50s

    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_13_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
    >:</
    0.14
    P
    0.13
     robot
    0.13
     કુલ
    0.12
     הע
    0.12
    곸
    0.12
    Lx
    0.12
     регу
    0.12
     leg
    0.12
    પ
    0.12
    POSITIVE LOGITS
    fficient
    0.15
    establish
    0.15
    resist
    0.14
    is
    0.13
    ffer
    0.13
    regions
    0.13
    cana
    0.13
    ylmethylsulfanyl
    0.13
    also
    0.13
    它的
    0.12
    Activations Density 0.016%

    No Known Activations