© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to outdoor trails, paths, and roads

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     great
    -1.09
    great
    -0.95
     nice
    -0.89
    Great
    -0.82
    nice
    -0.71
     Great
    -0.71
    GREAT
    -0.70
     excellent
    -0.69
     nicest
    -0.66
     GREAT
    -0.65
    POSITIVE LOGITS
     незавершена
    0.69
    LookAnd
    0.60
     bezeichneter
    0.58
    ]--;
    0.57
    CONSIN
    0.57
    uxxxx
    0.56
    untut
    0.54
    ()];
    0.52
    AndEndTag
    0.50
     الدولى
    0.50
    Activations Density 5.567%

    No Known Activations