INDEX

Explanations

code snippets along with associated terminology and error mentions

oai_token-act-pair · gemini-2.0-flash

programming code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 <=",

-0.71

 propOrder

-0.59

addCriterion

-0.56

:✨

-0.56

ThroughAttribute

-0.56

Tikang

-0.54

 AspNetCore

-0.50

enumi

-0.50

 autorytatywna

-0.47

IUrlHelper

-0.47

POSITIVE LOGITS

 بيها

0.64

jsonwebtoken

0.59

Koordinaten

0.59

TestingModule

0.57

 NSCoder

0.56

ulent

0.55

 发表于

0.55

 culturales

0.54

ocene

0.54

TestTools

0.53

Activations Density 11.753%

code snippets along with associated terminology and error mentions

programming code

No Comments

No Known Activations