© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217888
    Prev
    Next
    INDEX
    Explanations

    strengths

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ocratic
    0.38
    utorial
    0.37
    sus
    0.36
    ぶん
    0.36
    响应文件
    0.36
    ≌
    0.36
     paff
    0.35
    orient
    0.35
     гуляць
    0.35
    veg
    0.35
    POSITIVE LOGITS
     weakening
    0.47
     weak
    0.47
     weakened
    0.46
    弱
    0.46
     disadvantage
    0.44
     weakness
    0.43
     слабо
    0.43
     강화
    0.43
     stronger
    0.42
     weaken
    0.42
    Activations Density 0.008%

    No Known Activations