© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9336
    Prev
    Next
    INDEX
    Explanations

    breakdown of

    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_13_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
    mallow
    0.19
    োনাল
    0.18
     наступ
    0.18
    ቢያ
    0.17
    七
    0.17
    沔
    0.17
    铖
    0.17
    ታል
    0.17
    ній
    0.17
    kates
    0.17
    POSITIVE LOGITS
     JL
    0.17
     opined
    0.16
    asjon
    0.16
     PRODUCTION
    0.16
     sociological
    0.16
     unknowns
    0.16
     dialogue
    0.15
     respondent
    0.15
     strcmp
    0.15
    éros
    0.15
    Activations Density 0.567%

    No Known Activations