INDEX

Explanations

strings related to math and physics

oai_token-act-pair · gemini-2.0-flash

math and science text

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

 élevées

-0.49

mappedBy

-0.48

thâu

-0.45

 naturelles

-0.45

HtmlAttribute

-0.44

explique

-0.43

FunctionFlags

-0.43

󠁢

-0.43

 automatiques

-0.43

 anfitrión

-0.42

POSITIVE LOGITS

mybatisplus

0.58

Gambas

0.57

<bos>

0.56

djangoproject

0.55

!*\

0.55

complexContent

0.55

ulco

0.52

 begin

0.51

apimachinery

0.50

oredCriteria

0.50

Activations Density 0.386%

strings related to math and physics

math and science text

No Comments

No Known Activations