© 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. 7877
    Prev
    Next
    INDEX
    Explanations

    code and programming language snippets

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    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
     central
    -0.91
     regional
    -0.87
     region
    -0.84
     general
    -0.82
     global
    -0.81
     medium
    -0.79
     major
    -0.79
     domain
    -0.78
     standard
    -0.76
     primary
    -0.75
    POSITIVE LOGITS
     arrest
    0.71
     shot
    0.69
     pain
    0.69
     kiss
    0.68
     shots
    0.67
     attack
    0.66
     proof
    0.66
     talk
    0.66
     kick
    0.66
     crash
    0.66
    Activations Density 7.410%

    No Known Activations