© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    weapons and upgrades

    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_15_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
    ি
    0.47
     centrale
    0.44
     veinte
    0.43
     coffers
    0.42
     Savings
    0.42
     Ki
    0.42
     Key
    0.41
    надцати
    0.41
    ி
    0.41
     కి
    0.41
    POSITIVE LOGITS
    species
    0.47
     penyakit
    0.45
    uxxxx
    0.45
    OMB
    0.44
    Ibid
    0.43
    aqu
    0.43
    ariş
    0.42
    npm
    0.41
     Ärz
    0.41
    ardar
    0.41
    Activations Density 0.010%

    No Known Activations