INDEX

Explanations

the word "still".

oai_token-act-pair · gemini-2.0-flash

still

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 brancas

-0.71

rungsseite

-0.66

});*/

-0.61

จึง

-0.61

 Soit

-0.61

verwijspagina

-0.60

mybatisplus

-0.60

AutoScaleMode

-0.59

 JpaRepository

-0.59

 متعلقه

-0.57

POSITIVE LOGITS

snip

0.58

 didn

0.56

DANGER

0.54

iestety

0.54

ceptable

0.53

śnia

0.53

Booked

0.52

 Unfortunately

0.52

 capas

0.52

Unfortunately

0.52

Activations Density 0.329%

the word "still".

still

No Comments

No Known Activations