© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2875
    Prev
    Next
    INDEX
    Explanations

    words related to food, medical settings, sounds and materials

    oai_token-act-pair · gemini-2.0-flash

    soft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soft
    -2.88
     Soft
    -2.80
    soft
    -2.75
    Soft
    -2.72
     SOFT
    -2.63
     softer
    -2.33
    SOFT
    -2.31
     softness
    -2.31
     soften
    -2.02
     softens
    -1.97
    POSITIVE LOGITS
    AutoScaleMode
    0.46
     Wikidata
    0.45
    덱
    0.44
    arrows
    0.44
    cycline
    0.43
    inario
    0.42
    NEP
    0.41
    Asu
    0.40
    hibits
    0.40
     Mile
    0.39
    Activations Density 2.091%

    No Known Activations