© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    ; it

    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
    畴
    0.21
     losing
    0.20
    etum
    0.20
    იან
    0.20
    лишком
    0.19
    except
    0.19
    estimating
    0.18
    летов
    0.18
    λή
    0.17
    umé
    0.17
    POSITIVE LOGITS
     l
    0.22
     de
    0.21
     stato
    0.20
     sch
    0.20
     s
    0.19
    S
    0.19
     e
    0.18
     colch
    0.18
     che
    0.18
     NOVA
    0.18
    Activations Density 0.147%

    No Known Activations