INDEX

Explanations

quantitative references with comparatives, prepositions, and lists

oai_token-act-pair · gemini-2.0-flash

quantity

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-0.59

 Administrativna

-0.57

 ModelExpression

-0.50

 verschill

-0.50

réhen

-0.47

 PagesJaunes

-0.47

 województwie

-0.47

 başına

-0.45

Identyfik

-0.44

caid

-0.44

POSITIVE LOGITS

 weitere

0.93

vábbi

0.89

further

0.84

 weiteren

0.84

autres

0.84

 ExecuteAsync

0.81

urther

0.77

 additional

0.77

 further

0.76

########.

0.75

Activations Density 0.893%

quantitative references with comparatives, prepositions, and lists

quantity

No Comments

No Known Activations