© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    references to needs, calls for action, things that it's 'right now' time to do

    oai_token-act-pair · gemini-2.0-flash

    right now

    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
    now
    -1.71
     now
    -1.64
     Now
    -1.58
    Now
    -1.57
     Right
    -1.53
    Right
    -1.52
     Currently
    -1.51
    Currently
    -1.48
     currently
    -1.46
    currently
    -1.46
    POSITIVE LOGITS
     suitable
    0.50
    úgó
    0.50
    клопе
    0.47
    бливості
    0.46
    stylers
    0.46
    ChildScrollView
    0.45
    isons
    0.44
    +#+#
    0.44
    UserScript
    0.42
    ALLENG
    0.41
    Activations Density 8.849%

    No Known Activations