INDEX

Explanations

words related to buttons and code functions

oai_token-act-pair · gemini-2.0-flash

button

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

BeginContext

-0.55

 nahilalakip

-0.54

enumi

-0.53

addPreferredGap

-0.51

expandindo

-0.48

 unknownFields

-0.44

 disambiguazione

-0.43

 balade

-0.42

Button

-0.41

Vidite

-0.41

POSITIVE LOGITS

 expedi

0.59

Brainz

0.56

]-->

0.56

 AttributeSet

0.56

 Audiodateien

0.56

,‎

0.55

cmath

0.55

}-*/;

0.54

Насе

0.53

TintMode

0.53

Activations Density 3.539%

words related to buttons and code functions

button

No Comments

No Known Activations