INDEX

Explanations

dates, categories, and other structural elements of documents

oai_token-act-pair · gemini-2.0-flash

Biographical or encyclopedic text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 love

-0.68

AsUp

-0.66

love

-0.61

 loved

-0.50

LOVE

-0.50

ьаж

-0.50

allergenic

-0.50

 BoxFit

-0.49

ⓧ

-0.48

 LOVE

-0.48

POSITIVE LOGITS

principalColumn

0.69

becher

0.64

MetaType

0.63

that

0.61

 that

0.58

 Paglinawan

0.57

 DataTypes

0.57

 Signalez

0.57

 ModelExpression

0.57

 THAT

0.56

Activations Density 9.143%

dates, categories, and other structural elements of documents

Biographical or encyclopedic text

No Comments

No Known Activations