© 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. 137861
    Prev
    Next
    INDEX
    Explanations

    true followed by passion, art, age, lineage, origin, motives

    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
    Preprocessing
    0.58
    2
    0.55
    Nearby
    0.52
     sindaco
    0.52
     anatomic
    0.52
    哳
    0.52
     killings
    0.51
    জের
    0.51
     tactics
    0.51
     oscillators
    0.50
    POSITIVE LOGITS
    ဦ
    0.68
    is
    0.59
    ovič
    0.57
     định
    0.55
     constitu
    0.54
    起こ
    0.54
    ab
    0.53
    äume
    0.52
    ар
    0.52
    ül
    0.52
    Activations Density 0.001%

    No Known Activations