INDEX

Explanations

references to historical time periods and events

oai_token-act-pair · gemini-2.0-flash

numerals

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

tagHelperRunner

-0.51

ImageContext

-0.51

 счет

-0.48

Bea

-0.48

 Italij

-0.47

 Gehirn

-0.46

tack

-0.46

 Torque

-0.45

gant

-0.44

 facture

-0.43

POSITIVE LOGITS

 ExecuteAsync

0.82

AddTagHelper

0.76

MENAFN

0.59

 saites

0.59

نجليز

0.56

 mapStateToProps

0.55

Geplaatst

0.55

tanleria

0.54

 समीक्षाओं

0.53

enderror

0.51

Activations Density 1.073%

references to historical time periods and events

numerals

No Comments

No Known Activations