© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196322
    Prev
    Next
    INDEX
    Explanations

    centers around or focused on

    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
    含
    0.42
     brick
    0.37
     Horizontal
    0.36
     Bellamy
    0.36
     Lockdown
    0.36
    クセル
    0.36
     rue
    0.36
     hipótes
    0.35
     braiding
    0.35
    ⵢ
    0.35
    POSITIVE LOGITS
    nuclear
    0.43
    necessary
    0.41
     lucrative
    0.40
    declar
    0.39
    kin
    0.38
     NUCLEAR
    0.38
    prom
    0.38
    important
    0.37
    щиеся
    0.37
     உடன்
    0.37
    Activations Density 0.044%

    No Known Activations