INDEX

Explanations

words or phrases related to studies, analyses and results

oai_token-act-pair · gemini-2.0-flash

scientific research results

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

 result

-2.34

result

-1.98

 Result

-1.80

Result

-1.66

 RESULT

-1.63

RESULT

-1.41

 résultat

-1.40

 resultado

-1.38

 risultato

-1.30

 Ergebnis

-1.24

POSITIVE LOGITS

HtmlAttribute

0.80

 Waray

0.62

 Normdatei

0.61

 nakalista

0.57

devamını

0.57

 Савезне

0.53

+#+#

0.51

 SwitchCompat

0.50

SBATCH

0.50

RuleContext

0.50

Activations Density 6.833%

words or phrases related to studies, analyses and results

scientific research results

No Comments

No Known Activations