© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141813
    Prev
    Next
    INDEX
    Explanations

    less than X years

    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_12_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
    ي
    0.54
    🧉
    0.50
    AM
    0.45
     الواي
    0.44
    櫂
    0.43
    エット
    0.43
    イ
    0.42
    álen
    0.42
     recirculation
    0.42
     méthodique
    0.42
    POSITIVE LOGITS
    c
    0.55
     l
    0.45
     WWF
    0.45
    oss
    0.44
    la
    0.44
    ls
    0.42
     kepala
    0.42
     Wildlife
    0.42
    ena
    0.41
    oe
    0.41
    Activations Density 0.001%

    No Known Activations