© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8640
    Prev
    Next
    INDEX
    Explanations

    substrings that describe the plot of a fictional story

    oai_token-act-pair · gemini-2.0-flash

    Involved in complex situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    单
    -0.52
    Single
    -0.51
     Single
    -0.50
     single
    -0.49
    комиться
    -0.49
     tan
    -0.48
     Ste
    -0.46
    痹
    -0.44
    single
    -0.43
     und
    -0.43
    POSITIVE LOGITS
     Houſe
    0.80
     pleaſure
    0.79
     houſe
    0.75
     myſelf
    0.74
     itſelf
    0.73
     themſelves
    0.73
     Monfieur
    0.71
     ſeveral
    0.69
     purpoſe
    0.69
    PasswordEncoder
    0.69
    Activations Density 3.238%

    No Known Activations