INDEX

Explanations

root words "chlor," "or," and "stor."

oai_token-act-pair · gemini-2.0-flash

science

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

-0.58

tı

-0.57

glog

-0.55

)_/¯

-0.55

dra

-0.54

dı

-0.52

fclose

-0.52

dan

-0.51

{})

-0.51

POSITIVE LOGITS

FailureListener

0.61

expandindo

0.58

المكان

0.57

aarrggbb

0.56

 estekak

0.55

isContained

0.55

="@+

0.53

:✨

0.52

CPtr

0.52

Демографія

0.52

Activations Density 1.049%

root words "chlor," "or," and "stor."

science

No Comments

No Known Activations