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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167114
    Prev
    Next
    INDEX
    Explanations

    protocol

    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_56_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
    pessoa
    0.43
     gerente
    0.41
     designers
    0.39
    --"
    0.39
    Runs
    0.37
     responsáveis
    0.37
     pessoa
    0.36
    ையினர்
    0.36
    -*/
    0.36
     operador
    0.36
    POSITIVE LOGITS
    Protocol
    0.46
     Protocol
    0.45
     looks
    0.45
     protocol
    0.44
     correctly
    0.44
     correctamente
    0.43
    looks
    0.43
     corretamente
    0.42
     своего
    0.42
     correttamente
    0.42
    Activations Density 0.001%

    No Known Activations