INDEX

Explanations

words related to being acted upon or official procedures

oai_token-act-pair · gemini-2.0-flash

requests or actions

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

 Parcelable

-0.56

djangoproject

-0.55

 candidatura

-0.54

 dataSnapshot

-0.51

harapkan

-0.51

 navideñas

-0.50

 recib

-0.50

holtz

-0.50

 zostać

-0.50

 assurance

-0.49

POSITIVE LOGITS

 disambiguazione

0.57

createStatement

0.54

 للاسماء

0.52

RegisterType

0.52

SequentialGroup

0.50

)?;

0.49

rrggbb

0.49

[]:

0.49

 Excerpt

0.49

 확인함

0.48

Activations Density 8.488%

words related to being acted upon or official procedures

requests or actions

No Comments

No Known Activations