© 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. 5860
    Prev
    Next
    INDEX
    Explanations

    c and java programming code

    oai_token-act-pair · gemini-2.0-flash

    #

    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
    1
    -1.26
    2
    -1.24
    3
    -1.23
    6
    -1.20
    4
    -1.19
    8
    -1.19
    7
    -1.19
    5
    -1.18
    9
    -1.16
    0
    -1.14
    POSITIVE LOGITS
     poffe
    0.54
     houſe
    0.52
    <bos>
    0.52
     quelcon
    0.51
     uſed
    0.51
     lyre
    0.50
     hâte
    0.50
     Majefty
    0.50
     tranſ
    0.49
    ÁB
    0.49
    Activations Density 7.352%

    No Known Activations