© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7852
    Prev
    Next
    INDEX
    Explanations

    mentions of states and regions, possibly as part of a geographic place name.

    oai_token-act-pair · gemini-2.0-flash

    geographical locations and descriptions

    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
     BoxFit
    -0.66
    حياته
    -0.61
     InputDecoration
    -0.56
    Демографія
    -0.54
     Consolidation
    -0.53
    Iné
    -0.52
    AnchorTagHelper
    -0.52
     везе
    -0.52
     MotionEvent
    -0.51
    сумка
    -0.50
    POSITIVE LOGITS
     виправивши
    0.68
    TestFixture
    0.66
    oa̍t
    0.59
    righted
    0.51
     bezeichneter
    0.49
    ']],
    0.45
     nära
    0.44
     AssemblyTitle
    0.44
     sano
    0.43
    Proper
    0.42
    Activations Density 14.053%

    No Known Activations