INDEX

Explanations

mathematical notation and symbols

oai_token-act-pair · gemini-2.0-flash

bound

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hivat

-0.51

mişti

-0.50

oley

-0.49

vertreter

-0.49

vább

-0.48

 नाम

-0.48

endgroup

-0.48

läg

-0.47

 navn

-0.47

azon

-0.47

POSITIVE LOGITS

 ddelweddau

0.87

 CreateTagHelper

0.73

saraba

0.71

SharedDtor

0.65

 GenerationType

0.63

tagHelperRunner

0.63

InitVars

0.63

 Италијани

0.63

 betweenstory

0.63

 transfieras

0.62

Activations Density 19.671%

mathematical notation and symbols

bound

No Comments

No Known Activations