© 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. 3804
    Prev
    Next
    INDEX
    Explanations

    a broad range of topics, sometimes selecting just conjunctions, but often finding longer structures describing activities, resources, locations, and assistance.

    oai_token-act-pair · gemini-2.0-flash

    Academic/Technical writing

    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
     Many
    -0.66
    many
    -0.62
     Several
    -0.61
    Many
    -0.61
    Several
    -0.59
     muchos
    -0.58
     Numerous
    -0.58
     many
    -0.58
    several
    -0.57
    Numerous
    -0.56
    POSITIVE LOGITS
     a
    1.88
    a
    0.91
     number
    0.72
    number
    0.65
     variety
    0.63
    )');
    0.61
    }')
    0.61
    SequentialGroup
    0.60
    Number
    0.59
    }")
    0.59
    Activations Density 2.319%

    No Known Activations