INDEX

Explanations

in case

np_token-act-pair-logits · gemini-2.0-flash

conditional phrases, especially those using "case" or "if"

oai_token-act-pair · gemini-2.0-flash

Foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 OFDb

-0.69

 HasFactory

-0.69

EndTag

-0.64

undred

-0.64

rungsseite

-0.62

MigrationBuilder

-0.60

ConstraintMaker

-0.60

 يتيمه

-0.59

 kasarigan

-0.58

housie

-0.57

POSITIVE LOGITS

 olvidar

0.46

 >=",

0.45

ruptedException

0.45

 esquecer

0.45

oneg

0.43

 behö

0.42

ktı

0.41

withOpacity

0.40

 färg

0.39

ريقيا

0.39

Activations Density 2.410%

in case

conditional phrases, especially those using "case" or "if"

Foreign words

No Comments

No Known Activations