© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107059
    Prev
    Next
    INDEX
    Explanations

    Russian-ski suffix adjectives

    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_1_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
    t
    1.81
    the
    1.80
    s
    1.63
    er
    1.41
    f
    1.41
    tn
    1.35
    tw
    1.31
    ted
    1.27
    critical
    1.24
    2
    1.23
    POSITIVE LOGITS
     for
    1.18
     superficie
    1.16
     l
    1.10
    о
    1.10
     discourage
    1.09
     la
    1.08
     postpone
    1.08
     diminish
    1.07
    )،
    1.05
     ricerca
    1.05
    Activations Density 0.000%

    No Known Activations