© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    bullet points and website boilerplate text

    oai_token-act-pair · gemini-2.0-flash

    website information or code

    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
     this
    -2.67
     these
    -2.47
    this
    -2.05
    these
    -1.82
     queste
    -1.47
     این
    -1.44
     THIS
    -1.41
     questa
    -1.40
     questo
    -1.39
     diesen
    -1.37
    POSITIVE LOGITS
    GraphicsUnit
    0.68
    ThroughAttribute
    0.59
    uxxxx
    0.57
    HasOne
    0.56
    PYX
    0.56
    ngdoc
    0.55
    rungsseite
    0.54
    ⓧ
    0.54
    Translatef
    0.54
     bezeichneter
    0.53
    Activations Density 6.402%

    No Known Activations