INDEX

Explanations

code syntax, particularly Java code related to constants, static variables, and Android imports

oai_token-act-pair · gemini-2.0-flash

final

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

UnusedPrivate

-0.76

SharedCtor

-0.75

kháu

-0.69

pherals

-0.60

NameInMap

-0.60

Vidite

-0.59

 оригіналу

-0.55

########.

-0.55

 snippetHide

-0.53

openzeppelin

-0.53

POSITIVE LOGITS

/\.

0.63

 BoxFit

0.54

 Bioaccumulative

0.53

 Audiodateien

0.51

zinho

0.50

 ब्रेकडाउन

0.49

uldade

0.47

ideae

0.47

lucene

0.47

="@+

0.46

Activations Density 1.527%

code syntax, particularly Java code related to constants, static variables, and Android imports

final

No Comments

No Known Activations