INDEX

Explanations

words or symbols connected with hyphens

oai_token-act-pair · gemini-2.0-flash

-

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-1.38

-0.71

-(

-0.63

-0.62

-/

-0.61

-<

-0.58

-[

-0.58

-0.57

-0.54

POSITIVE LOGITS

 itſelf

1.04

StoryboardSegue

0.81

ImageContext

0.78

存于互联网档案馆

0.77

tagHelperRunner

0.75

 beginnetje

0.75

 ་་

0.73

 disambiguazione

0.73

 ―――――

0.72

 raiſ

0.71

Activations Density 1.005%

words or symbols connected with hyphens

-

No Comments

No Known Activations