© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116832
    Prev
    Next
    INDEX
    Explanations

    parameters or data structures

    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_27_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
    紂
    0.41
     insult
    0.40
    abases
    0.38
     Ontology
    0.38
     acteurs
    0.38
    長的
    0.38
     కళ
    0.38
     ontology
    0.37
     realizó
    0.37
     correctAnswer
    0.36
    POSITIVE LOGITS
    coef
    0.39
    ]$,
    0.38
     anuv
    0.35
    Eh
    0.34
    楖
    0.34
    None
    0.34
    itm
    0.34
    invert
    0.34
     সমান
    0.33
     समान
    0.33
    Activations Density 0.002%

    No Known Activations