INDEX

Explanations

words indicating scientific data collection and presentation, along with some additional common words and symbols in that context

oai_token-act-pair · gemini-2.0-flash

Scientific research papers

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

endphp

-0.65

Biographie

-0.63

Билгалдахарш

-0.54

tanleria

-0.54

intios

-0.54

 nahilalakip

-0.53

 فريبيس

-0.53

avigation

-0.52

Kaynakça

-0.52

 Meksiku

-0.51

POSITIVE LOGITS

<%@

0.57

 NSCoder

0.55

rådet

0.51

näm

0.50

uxxxx

0.50

invokeLater

0.50

 Palatine

0.49

PackageManager

0.48

 éché

0.47

SMP

0.47

Activations Density 3.408%

words indicating scientific data collection and presentation, along with some additional common words and symbols in that context

Scientific research papers

No Comments

No Known Activations

words indicating scientific data collection and presentation, along with some additional common words and symbols in that context

Scientific research papers

No Comments

No Known Activations