© 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. 130686
    Prev
    Next
    INDEX
    Explanations

    tattoo ideas

    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
    1
    1.38
    kan
    1.35
    2
    1.29
    ک
    1.18
    3
    1.12
    larının
    1.11
    ่
    1.09
     Lihat
    1.07
    ż
    1.04
    ns
    1.03
    POSITIVE LOGITS
    o
    1.19
     δύο
    1.11
     malicious
    1.06
     fluctu
    1.05
     debilit
    1.03
     flexion
    1.03
     conducir
    1.02
     maliciously
    1.02
     medall
    1.01
     culp
    1.01
    Activations Density 0.000%

    No Known Activations