© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42514
    Prev
    Next
    INDEX
    Explanations

    assuming you

    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_22_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
    Кар
    0.45
    ष्
    0.43
    명을
    0.43
    Gi
    0.43
    Potato
    0.42
    eliac
    0.40
    HIR
    0.39
    𝐩
    0.39
    𝙥
    0.39
    Army
    0.38
    POSITIVE LOGITS
     hurting
    0.44
    比べて
    0.36
     effectués
    0.36
     ряда
    0.36
     ঝামে
    0.36
    蘅
    0.36
    ፏ
    0.35
     vocês
    0.35
     vatt
    0.35
    において
    0.34
    Activations Density 0.006%

    No Known Activations