© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34859
    Prev
    Next
    INDEX
    Explanations

    "I" followed by verbs

    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_7_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
    }$\
    0.41
    нки
    0.41
    သုံး
    0.39
     personalize
    0.39
     sakura
    0.38
     želite
    0.38
     infringe
    0.38
     commandment
    0.38
    hitth
    0.38
    ៈ
    0.38
    POSITIVE LOGITS
    g
    0.66
    d
    0.63
    i
    0.49
    v
    0.48
    x
    0.48
    h
    0.48
    S
    0.45
    FC
    0.44
    ي
    0.44
     the
    0.44
    Activations Density 0.007%

    No Known Activations