© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49214
    Prev
    Next
    INDEX
    Explanations

    word endings

    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_55_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
    ISH
    0.45
    ish
    0.44
    stage
    0.43
    𝐬
    0.42
    esh
    0.42
    ishly
    0.41
    士
    0.41
     Hash
    0.41
    ｓ
    0.40
    ishes
    0.40
    POSITIVE LOGITS
    hed
    1.28
    hi
    1.23
    hip
    1.17
    hes
    1.12
    hing
    1.05
    hee
    1.02
    her
    1.01
    he
    0.98
    hen
    0.95
    hest
    0.95
    Activations Density 0.003%

    No Known Activations