INDEX

Explanations

code snippets containing conditional statements with identifiers

oai_token-act-pair · gemini-2.0-flash

Code/technical context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

un

-1.20

Uns

-1.09

uns

-1.08

Un

-1.03

未

-1.02

Un

-1.00

unt

-0.98

Uns

-0.96

 untouched

-0.94

uns

-0.94

POSITIVE LOGITS

rungsseite

0.60

KEYCODE

0.59

ViewFeatures

0.57

expandindo

0.57

complexContent

0.55

mstyle

0.55

PullParser

0.54

 vilja

0.53

 Réponses

0.53

 velkommen

0.53

Activations Density 0.708%

code snippets containing conditional statements with identifiers

Code/technical context

No Comments

No Known Activations