© 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. 1342
    Prev
    Next
    INDEX
    Explanations

    instances of disagreement and experimental research

    oai_token-act-pair · gemini-2.0-flash

    technical/academic texts

    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
     full
    -0.92
     exact
    -0.79
     fully
    -0.75
     voller
    -0.75
    exact
    -0.74
     FULL
    -0.74
    full
    -0.72
    fully
    -0.72
     complete
    -0.71
     EXACT
    -0.70
    POSITIVE LOGITS
     resourceCulture
    0.77
    AndroidJUnit
    0.75
     JpaRepository
    0.66
    ChildScrollView
    0.60
     un
    0.59
    municipi
    0.59
    évaluateur
    0.59
    醐
    0.59
    zzleHttp
    0.58
    তথ্যসূত্র
    0.57
    Activations Density 8.449%

    No Known Activations