© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    code with loops and matrix indexing.

    oai_token-act-pair · gemini-2.0-flash

    Brackets and symbols

    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
     vPvB
    -0.74
    BeginContext
    -0.70
     GenerationType
    -0.66
    nologue
    -0.65
    mergeFrom
    -0.65
    gameserver
    -0.65
    AutoField
    -0.64
     shutterstock
    -0.60
     RISERV
    -0.60
     RSSSF
    -0.58
    POSITIVE LOGITS
    Jx
    0.53
    Cx
    0.52
    Fq
    0.51
    Tn
    0.50
    Sx
    0.50
    Lx
    0.50
    Ju
    0.49
    Rb
    0.48
    rms
    0.48
    Fx
    0.48
    Activations Density 13.528%

    No Known Activations