© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    first person perspective combined with uncertainty

    oai_token-act-pair · gemini-2.0-flash

    Programming/troubleshooting errors

    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
     right
    -1.33
     correct
    -1.30
     WRONG
    -1.24
     Wrong
    -1.23
     Right
    -1.17
    correct
    -1.16
    right
    -1.15
    Wrong
    -1.15
    Right
    -1.13
     incorrect
    -1.13
    POSITIVE LOGITS
    plain
    0.60
     base
    0.59
    idez
    0.52
     Completely
    0.51
     completely
    0.51
    base
    0.48
    +#+#
    0.47
    tagHelperRunner
    0.47
     transfieras
    0.47
     Base
    0.46
    Activations Density 2.514%

    No Known Activations