© 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. 167180
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Till
    0.45
     Till
    0.45
    till
    0.42
     до
    0.39
     Spect
    0.38
     Til
    0.38
     puriso
    0.38
    َا
    0.37
     kepentingan
    0.37
     sampe
    0.37
    POSITIVE LOGITS
     organising
    0.52
    knowing
    0.50
     knowing
    0.45
     arranging
    0.44
     optimised
    0.44
     need
    0.43
     organisational
    0.43
     know
    0.41
     formulating
    0.41
    reading
    0.40
    Activations Density 0.001%

    No Known Activations