INDEX

Explanations

words associated with pressing a button or key, or academic presses

oai_token-act-pair · gemini-2.0-flash

press

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 press

-2.81

Press

-2.59

 Press

-2.59

press

-2.50

 PRESS

-2.38

 presses

-2.00

PRESS

-1.98

 pressed

-1.81

 presse

-1.80

 Presse

-1.77

POSITIVE LOGITS

TypedDataSet

0.68

vábbi

0.57

ÈME

0.56

tagHelperRunner

0.56

ScopeManager

0.55

istered

0.55

چار

0.54

цездатний

0.54

 inconn

0.54

ViewImports

0.53

Activations Density 9.196%

words associated with pressing a button or key, or academic presses

press

No Comments

No Known Activations