© 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. 14608
    Prev
    Next
    INDEX
    Explanations

    scientific research papers, including figures, tables, references, experiments, and results.

    oai_token-act-pair · gemini-2.0-flash

    single digit

    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
     Theſe
    -0.93
     defaultstate
    -0.90
     ComVisible
    -0.90
     Monfieur
    -0.87
     himſelf
    -0.85
     resourceCulture
    -0.84
     itſelf
    -0.84
     pleaſure
    -0.82
     myſelf
    -0.82
     becauſe
    -0.82
    POSITIVE LOGITS
    3
    1.69
    4
    1.66
    5
    1.59
    2
    1.58
    6
    1.45
    1
    1.37
    7
    1.30
    8
    1.28
    9
    1.19
    0
    1.01
    Activations Density 40.891%

    No Known Activations