INDEX

Explanations

descriptions of inventions and other patented material.

oai_token-act-pair · gemini-2.0-flash

of

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

complexContent

-0.70

adaptiveStyles

-0.67

IsContent

-0.63



-0.63

رشف

-0.63

AddHtmlAttribute

-0.61

Архівовано

-0.59

 mergeFrom

-0.59

Portale

-0.57

CGRectMake

-0.56

POSITIVE LOGITS

fromnode

0.52

 Pavia

0.47

URER

0.44

stdc

0.44

تفصیلات

0.43

 appréci

0.42

americana

0.42

 ejercer

0.42

úmeros

0.41

ClientSize

0.41

Activations Density 4.977%

descriptions of inventions and other patented material.

of

No Comments

No Known Activations