© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5967
    Prev
    Next
    INDEX
    Explanations

    end punctuation, potentially in dialogue

    oai_token-act-pair · 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
     and
    -2.73
    and
    -0.98
     or
    -0.96
     그리고
    -0.95
    และ
    -0.93
     и
    -0.89
    そして
    -0.84
    および
    -0.82
     và
    -0.82
     وم
    -0.81
    POSITIVE LOGITS
    Et
    0.57
     Et
    0.52
     étoient
    0.49
    ANDS
    0.48
    avantage
    0.46
    pecified
    0.44
    Tikang
    0.43
    ANDRO
    0.42
    und
    0.42
    luß
    0.41
    Activations Density 2.939%

    No Known Activations