© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35264
    Prev
    Next
    INDEX
    Explanations

    Oswald, leasehold, conflict

    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_3_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
     It
    0.71
    た
    0.66
    G
    0.63
    h
    0.63
    Mz
    0.61
    alco
    0.60
    </h3>
    0.59
    ணை
    0.59
    y
    0.58
    an
    0.57
    POSITIVE LOGITS
    ה
    0.62
     predictions
    0.61
    Innen
    0.61
     compelled
    0.61
     reputations
    0.59
    ne
    0.59
     fullness
    0.58
     groundwork
    0.58
     conflict
    0.57
     conflicto
    0.56
    Activations Density 0.001%

    No Known Activations