© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    political commentary, specifically around elections and historical conflicts.

    oai_token-act-pair · gemini-2.0-flash

    tactics and strategies

    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
     CreateTagHelper
    -0.61
    interopRequire
    -0.56
     Trick
    -0.56
    tonode
    -0.56
    AnchorStyles
    -0.56
     tactics
    -0.55
     tactic
    -0.55
    hoga
    -0.55
    ModelAndView
    -0.54
     Tactics
    -0.54
    POSITIVE LOGITS
    abestanden
    0.52
    /***/
    0.51
     referenties
    0.47
    .*")]
    0.47
     get
    0.46
     հղումներ
    0.44
    urbs
    0.44
     Get
    0.42
     <=",
    0.41
     Freiheit
    0.41
    Activations Density 10.529%

    No Known Activations