© 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. 14564
    Prev
    Next
    INDEX
    Explanations

    phrases containing a number followed by a hyphen

    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
    AndEndTag
    -0.77
    MessageOf
    -0.69
    OGND
    -0.69
     SPDX
    -0.61
    UnusedPrivate
    -0.58
     CWE
    -0.55
    AlterField
    -0.52
    endphp
    -0.51
     nakalista
    -0.51
     GoogleFonts
    -0.50
    POSITIVE LOGITS
    way
    0.61
    worlds
    0.54
     to
    0.53
    plane
    0.51
    course
    0.50
    tenths
    0.49
    rimas
    0.49
    hills
    0.48
    lined
    0.48
    angles
    0.47
    Activations Density 4.701%

    No Known Activations