© 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. 14981
    Prev
    Next
    INDEX
    Explanations

    numbers as well as formatting that often accompanies numbers, times and dates.

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     myſelf
    -0.45
     itſelf
    -0.43
     Efq
    -0.39
    ſelves
    -0.36
     raiſ
    -0.30
    ſelf
    -0.28
     uſe
    -0.28
     pleaſure
    -0.27
    ^(@)
    -0.22
     faſt
    -0.22
    POSITIVE LOGITS
    1
    1.19
    2
    1.16
    0
    1.12
    3
    1.09
    5
    1.07
    6
    1.06
    4
    1.05
    7
    1.02
    9
    1.02
    8
    1.01
    Activations Density 21.895%

    No Known Activations